Remote Founding AI Agent Harness Engineer

Bolder Apps; United States; Remote; USD 180,000 - 240,000; Full time

Benefits offered by this job

Competitive compensation

Equity

Direct line to founder

Remote work anywhere in the US

Job summary

Bolder Apps is seeking a senior Founding Harness Engineer for a partner startup building an AI coworker that operates inside team tools to get real work done. Remote-friendly anywhere in the US, with Pacific time overlap preferred, the role starts as a contract with a path to full-time once proven.

You will design the agent runtime, manage prompts, tests, and guardrails, and work directly with the founder and early users to ship reliable behavior.

Qualifications

• Shipped tool-using LLM agents to real users.
• Experience building eval and regression suites for LLM behavior.
• Know safe tool execution, prompt injection, and multi-tenant data risk.
• Strong backend skills in Python or TypeScript.
• Ability to take a fuzzy problem from prototype to production and explain tradeoffs.

Responsibilities

• Build the agent runtime: context, tool choice, approval waits, and knowing when to act, ask, or stay quiet
• Write and keep tuning the system prompts. Proactive is great. Spamming the team channel is not
• Own the eval and regression harness. Prompt changes are code, so they get tested like code
• Make long-running work survive interruptions, retries, and the occasional flaky API
• Put the guardrails in: approval gates for risky actions and strict separation between customers' data
• Work directly with the founder and early users, and turn what you hear into shipped behavior
• You've shipped tool-using LLM agents to real users in production. Demos and prompt wrappers don't count
• Good instincts for agent initiative, and the test results to back them up

Skills

LLM agent development

Tool-using agents

Prompt engineering

Backend development

Distributed systems

Tools

Python

TypeScript

LangSmith

Langfuse

Braintrust

Slack

Gmail

Notion

Linear

Job description

Bolder Apps is seeking a senior Founding Harness Engineer for a partner startup building an AI coworker that operates inside team tools to get real work done. Remote-friendly anywhere in the US, with Pacific time overlap preferred, the role starts as a contract with a path to full-time once proven.

You will design the agent runtime, manage prompts, tests, and guardrails, and work directly with the founder and early users to ship reliable behavior.